© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5715
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    poor
    -0.44
    []
    -0.44
     kaybet
    -0.43
    MockMvc
    -0.42
     banho
    -0.41
     inextrica
    -0.40
    gdx
    -0.40
    Haut
    -0.40
    поло
    -0.39
     isother
    -0.39
    POSITIVE LOGITS
     NSCoder
    0.92
    новништво
    0.81
    TintMode
    0.79
    Diweddarwch
    0.73
    tagHelperRunner
    0.72
    +#+
    0.70
     nahilalakip
    0.69
    Vidite
    0.66
     ErrIntOverflow
    0.64
     كومونز
    0.63
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.